© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118093
    Prev
    Next
    INDEX
    Explanations

    3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     делает
    -0.07
     つい
    -0.06
     makes
    -0.06
    clinton
    -0.06
     membuat
    -0.06
     взрос
    -0.06
     childlike
    -0.06
     دقیق
    -0.06
    ungy
    -0.06
     childbirth
    -0.06
    POSITIVE LOGITS
    ナー
    0.06
    欲しい
    0.06
     its
    0.06
     is
    0.06
     sospe
    0.06
     was
    0.06
     δεν
    0.06
     The
    0.06
     মজুদ
    0.06
     adjunct
    0.06
    Activations Density 0.005%

    No Known Activations